© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 11900
    Prev
    Next
    INDEX
    Explanations

    titles and positions of authority within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципалі
    -0.59
     الرياضيه
    -0.58
     Roskov
    -0.57
     հղումներ
    -0.57
    лтемелер
    -0.54
    الحياه
    -0.53
    addPreferredGap
    -0.52
     Вікі
    -0.51
    nastics
    -0.50
    Билгалдахарш
    -0.50
    POSITIVE LOGITS
     Director
    0.59
    Director
    0.55
     directora
    0.50
     Superintendent
    0.49
     CURIAM
    0.49
     director
    0.49
    director
    0.47
     Sheriff
    0.44
     superintendent
    0.42
    Superintendent
    0.41
    Activations Density 0.112%

    No Known Activations